Outcomes

get_impact

Run-over-run improvement: score series, questions flipped or declined, and the measured effect of completed tasks.

readReads only. Annotated read-only, so a client can call it without asking.

Plan: Grow and above
Rate cost: 5 units
REST: GET /projects/{project_id}/impact

Try asking

“Did the pages we published actually change anything?”

get_impact

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_impact",
    "arguments": {
      "project_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
    }
  }
}

structuredContent

{
  "content": [
    {
      "type": "text",
      "text": "…the same JSON, as text…"
    }
  ],
  "structuredContent": {
    "status": "ready",
    "runs_observed": 12,
    "probes_measured": 480,
    "prompts_tracked": 40,
    "baseline_runs": 2,
    "current_runs": 2,
    "baseline_score": 28.4,
    "current_score": 34.1,
    "score_delta": 5.7,
    "significant": true,
    "trend_direction": "up",
    "series": [
      {
        "date": "2026-09-04",
        "geo_score": 28.4,
        "visibility": 41.3,
        "win_rate": 22.5,
        "mention_rate": 41.3,
        "citation_rate": 11.3,
        "probes": 40
      },
      {
        "date": "2026-09-20",
        "geo_score": 34.1,
        "visibility": 47.5,
        "win_rate": 30,
        "mention_rate": 47.5,
        "citation_rate": 15,
        "probes": 40
      }
    ],
    "prompts": {
      "flipped": 3,
      "improved": 6,
      "declined": 2,
      "stable": 27,
      "new": 2,
      "movers": [
        {
          "prompt_id": "0e9a7c55-2b3d-4c1e-8f6a-9d0b1c2e3f4a",
          "text": "best invoicing software for freelancers in India",
          "baseline_win_rate": 0,
          "current_win_rate": 50,
          "delta_pp": 50,
          "state": "flipped"
        }
      ]
    },
    "prompt_history": [
      {
        "prompt_id": "0e9a7c55-2b3d-4c1e-8f6a-9d0b1c2e3f4a",
        "text": "best invoicing software for freelancers in India",
        "state": "flipped",
        "win_rates": [
          0,
          50
        ]
      }
    ],
    "tasks": {
      "open": 6,
      "in_progress": 2,
      "resolved": 4,
      "measured": 3,
      "items": [
        {
          "id": "c1d2e3f4-5a6b-47c8-99d0-1e2f3a4b5c6d",
          "title": "Comparison page — \"best invoicing software for freelancers in India\"",
          "type": "comparison",
          "impact": "high",
          "status": "resolved",
          "updated_at": "2026-09-16T09:41:00Z",
          "prompt_text": "best invoicing software for freelancers in India",
          "baseline_win_rate": 0,
          "current_win_rate": 50,
          "delta_pp": 50,
          "state": "flipped"
        }
      ]
    }
  },
  "isError": false
}

Arguments

Passed as the tool call's arguments.

project_idstringrequired

The project to read, from list_projects.

Result

The same object as Get impact, returned as structured output.

statusstring

ready from the third run; before that there's no baseline to compare against and the scores are null.

Values:no_datacollecting_baselineready

runs_observedinteger

Runs in the window.

probes_measuredinteger

Answers behind the comparison.

prompts_trackedinteger

Prompts followed.

baseline_runsinteger

Runs pooled into the baseline.

current_runsinteger

Runs pooled into the current score.

baseline_scorenumbernullable

GEO score at the start, 0–100.

current_scorenumbernullable

GEO score now, 0–100.

score_deltanumbernullable

current_score − baseline_score, in points.

significantboolean

True when the change is larger than both scores' confidence intervals — otherwise treat it as noise.

trend_directionstring

stable below 2 points of change.

Values:updownstable

seriesobject[]

One point per run, oldest first.

+Show child attributes

datestring

When the run started, as YYYY-MM-DD.

geo_scorenumber

0–100.

visibilitynumber

0–100.

win_ratenumber

Share of the run's answers won, 0–100.

mention_ratenumber

Share that named the brand, 0–100.

citation_ratenumber

Share that cited the brand's domains, 0–100.

probesinteger

Answers in the run.

promptsobject

How the tracked prompts moved between baseline and now.

+Show child attributes

flippedinteger

Prompts that went from never winning to winning at least half the time.

improvedinteger

Prompts up by 10 points or more.

declinedinteger

Prompts down by 10 points or more.

stableinteger

Prompts that moved less than 10 points.

newinteger

Prompts with no baseline to compare against.

moversobject[]

The biggest movers, up to 50.

+Show child attributes

prompt_idstring

Prompt id.

textstring

The prompt.

baseline_win_ratenumbernullable

Win rate then, 0–100.

current_win_ratenumber

Win rate now, 0–100.

delta_ppnumbernullable

The change, in percentage points.

statestring

Which bucket it fell into.

Values:flippedimproveddeclinedstablenew

prompt_historyobject[]

Per-prompt win rate across the runs in series, up to 50 prompts.

+Show child attributes

prompt_idstring

Prompt id.

textstring

The prompt.

statestringnullable

Its bucket, once there's a baseline.

win_ratesnumber[]

One entry per run in series, same order, 0–100. Null where the prompt wasn't asked in that run.

tasksobject

Content-queue work set against what it moved.

+Show child attributes

openinteger

Open tasks.

in_progressinteger

Tasks in progress.

resolvedinteger

Tasks marked done.

measuredinteger

Done tasks with a before-and-after reading.

itemsobject[]

Tasks in progress or done, biggest effect first.

+Show child attributes

idstring

Task id.

titlestring

The task.

typestring

Kind of work.

impactstring

Size of the prize.

Values:highmediumlow

statusstring

Its status.

updated_atstring

Last change (ISO 8601).

prompt_textstringnullable

The prompt it addressed.

baseline_win_ratenumbernullable

Win rate before, 0–100.

current_win_ratenumbernullable

Win rate after, 0–100.

delta_ppnumbernullable

The change, in percentage points.

statestring

What the measurement says.

Values:measuringflippedimproveddeclinedno_change

Errors

404 not_found	The project or item doesn't exist in this workspace. A project from another workspace also returns 404, never 403.
422 invalid_request	A parameter or body field is missing or has the wrong type or value. The message names the field. Also returned when a write would pass the plan's prompt limit.
401 unauthorized	No key was sent, or the key is unknown, revoked or expired, or the member who created it has left the workspace or been deactivated.
402 plan_required	The workspace's plan doesn't include API access. It's included on Grow, Scale and Custom.
403 workspace_not_approved	The workspace is still waiting for approval, or wasn't approved.
429 rate_limited	Too many requests this minute. Wait for the number of seconds in the `Retry-After` header, then retry.

Every code, and what to retry, is in Errors.

Failures arrive as a tool error — isError: true with code: message as text. See Using the tools.